Instructions to use HASAN55/bert-finetuned-squad with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use HASAN55/bert-finetuned-squad with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "question-answering" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("question-answering", model="HASAN55/bert-finetuned-squad")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("HASAN55/bert-finetuned-squad") model = AutoModelForQuestionAnswering.from_pretrained("HASAN55/bert-finetuned-squad", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Training in progress epoch 2
Browse files- README.md +5 -4
- tf_model.h5 +1 -1
README.md
CHANGED
|
@@ -14,13 +14,13 @@ probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
-
- Train Loss:
|
| 18 |
-
- Train End Logits Accuracy: 0.
|
| 19 |
-
- Train Start Logits Accuracy: 0.
|
| 20 |
- Validation Loss: 0.0
|
| 21 |
- Validation End Logits Accuracy: 0.0
|
| 22 |
- Validation Start Logits Accuracy: 0.0
|
| 23 |
-
- Epoch:
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
@@ -48,6 +48,7 @@ The following hyperparameters were used during training:
|
|
| 48 |
|:----------:|:-------------------------:|:---------------------------:|:---------------:|:------------------------------:|:--------------------------------:|:-----:|
|
| 49 |
| 2.7873 | 0.3380 | 0.3363 | 0.0 | 0.0 | 0.0 | 0 |
|
| 50 |
| 1.2275 | 0.6718 | 0.6520 | 0.0 | 0.0 | 0.0 | 1 |
|
|
|
|
| 51 |
|
| 52 |
|
| 53 |
### Framework versions
|
|
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
+
- Train Loss: 0.8417
|
| 18 |
+
- Train End Logits Accuracy: 0.7725
|
| 19 |
+
- Train Start Logits Accuracy: 0.7444
|
| 20 |
- Validation Loss: 0.0
|
| 21 |
- Validation End Logits Accuracy: 0.0
|
| 22 |
- Validation Start Logits Accuracy: 0.0
|
| 23 |
+
- Epoch: 2
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
|
|
| 48 |
|:----------:|:-------------------------:|:---------------------------:|:---------------:|:------------------------------:|:--------------------------------:|:-----:|
|
| 49 |
| 2.7873 | 0.3380 | 0.3363 | 0.0 | 0.0 | 0.0 | 0 |
|
| 50 |
| 1.2275 | 0.6718 | 0.6520 | 0.0 | 0.0 | 0.0 | 1 |
|
| 51 |
+
| 0.8417 | 0.7725 | 0.7444 | 0.0 | 0.0 | 0.0 | 2 |
|
| 52 |
|
| 53 |
|
| 54 |
### Framework versions
|
tf_model.h5
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 431158224
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37d1954f1b7380d216eb38113f2f6f1ceeb223eb356f883f40c01e7bc472bcb6
|
| 3 |
size 431158224
|